Can Desktop PC · GeForce RTX 3090 · 32 GB RAM run Qwen3.5 122B-A10B?
24 GB VRAM + 32 GB RAM · 936 GB/s memory bandwidth · Qwen3.5 122B-A10B has 125B parameters (10B active per token).
Short answer
No. It doesn't fit in memory.
Needs ≈59 GB but only ≈47 GB of VRAM + system RAM is available after the OS and other apps.
Why it doesn’t fit
Even its smallest practical version (Q3_K_M) needs about 59 GB for the model, its context memory and the runtime. After Windows (≈4.5 GB), a browser with a few tabs (≈3.0 GB) and Open WebUI (≈1.0 GB), Desktop PC · GeForce RTX 3090 · 32 GB RAM has about 47 GB left, so it’s 12 GB short.
Ways to make it work
Close everything else
Not enough on its own: with every other app closed it’s still about 9.0 GB short.
Pick a smaller model from the same family
Get more memory
You’d want at least 67 GB of VRAM plus RAM in total. The machines below are the cheapest that run it comfortably.
Check your exact setup
These pages assume typical settings. A shorter context or a lighter chat app can change the answer.
Check Desktop PC · GeForce RTX 3090 · 32 GB RAM
The same applies to every workload we rate (chat, coding questions, coding in a repository, agentic coding and long documents): they all need at least as much memory as chat.
Other models for Desktop PC · GeForce RTX 3090 · 32 GB RAM
The best-rated models for chat on this machine.
- Qwen3.6 35B-A3B210–280 tok/sExcellent
- Gemma 4 26B-A4B140–190 tok/sExcellent
- LFM2.5 24B-A2B300–410 tok/sExcellent
- Qwen3.5 35B-A3B210–280 tok/sExcellent
- GLM-4.7-Flash (30B-A3B)210–280 tok/sExcellent
- gpt-oss-20b≈150 tok/sExcellent
Cheapest machines for Qwen3.5 122B-A10B
Hardware rated comfortable or better for chat, lowest price first.
- Ryzen AI Max+ 395 mini PC / Framework Desktop · 128 GB$2,000 · 25–30 tok/sExcellent
- Mac Studio M2 Max 96 GB$3,799 · 30–40 tok/sExcellent
- MacBook Pro M3 Max 96 GB$3,999 · 25–35 tok/sExcellent
- Mac Studio M5 Max 128 GB$4,099 · 35–55 tok/sExcellent
- Mac Studio M4 Max 128 GB$4,099 · 35–45 tok/sExcellent
- MacBook Pro M2 Max 96 GB$5,099 · 30–40 tok/sExcellent
Same chip, other memory: 64 GB
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.